Context
256K
Max output
256K
Serving providers
1
Cheapest input
$0.14 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis
Speed & latency
Output speed
35 t/s
tokens / second
Time to first token
1.06s
latency
Headline indices
43.4
of 100
14.4
of 100
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
AA-Briefcase0%
CritPt1%default
EvalComputeProxy2264.8default
GDPval804.0default
GPQA Diamond86%default
Humanity's Last Exam23%default
IFBench76%default
IT-Bench SRE37%default
Long-Context Reasoning62%default
MMMU-Pro73%default
Omniscience-45.4default
SciCode43%default
TerminalBench Hard36%default
TerminalBench v2.143%default
τ-bench Banking15%default
τ²-bench66%reasoning: false

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
Amazon BedrockCheapest$0.14$0.401
ComponentUnitStandardBatchCached
Text input/1M tok$0.1400
Text output/1M tok$0.4000

Price history

input + output $/1M since we started tracking
Input Output
$0.000$0.100$0.200$0.300$0.400Jun 12Jun 22$0.400$0.140

Cost calculator

estimate your monthly spend on this model
$60
estimated / month

Model IDs

copy the exact identifier for your platform
bedrock_mantle/google.gemma-4-31b

Frequently asked questions

Gemma 4 31B pricing, context and availability

How much does Gemma 4 31B cost?

Gemma 4 31B costs $0.14 per 1M input tokens and $0.40 per 1M output tokens at its cheapest provider via Amazon Bedrock.

What is the context window of Gemma 4 31B?

Gemma 4 31B accepts up to 256K tokens of context and can return up to 256K output tokens.

What can Gemma 4 31B do?

Gemma 4 31B supports image input (vision), tool use and reasoning.

Other Google models

compare pricing across the Google lineup
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI